JPS63284641A - Expert trouble diagnosis system - Google Patents

Abstract

PURPOSE:To intuitively recognize the probability for the factor of a trouble and also to shorten the trouble diagnosing time, by sorting the factors of the trouble obtained from the trouble diagnosis results by coloring in response to the degree of probability. CONSTITUTION:A display device 6 sorts roughly a trouble state and displays these sorted states on an initial screen for selection of the trouble state. Then the trouble state is supplied when an operator selects the item numbers 1-5 via an input device 1. An inference engine 3 infers the trouble factor based on the data stored in a knowledge base 4. Thus a coloring display processing part 7 decides the colors to be displayed in the color display areas of a display screen according to the probability of each trouble factor. An output processing part 5 produces the picture display data to display by coloring the trouble factors and their probabilities and displays these factors and probabilities on the device 6.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to an expert failure diagnosis system, and more particularly to an expert failure diagnosis system that displays failure probabilities in an easy-to-understand manner.

[Prior Art] An expert failure diagnosis system displays possible failure causes together with their probabilities as a result of failure diagnosis. FIG. 4 is a block diagram of a conventional expert failure diagnosis system. In Figure 4, (1) is an input device such as a keyboard through which the operator inputs data such as failure status, (2) is an input processing unit that takes in data input from input device (1), and (3) is an input device. An inference engine (5) infers the cause of failure based on the data imported by the processing unit (2) and data stored in the knowledge base (4) and outputs the inference result as a diagnosis result. (3) is an output processing unit that generates data for displaying the diagnosis results in text, and (6) is a CRT that displays the diagnosis results.
It is a display device such as a display.

Next, the operation of the conventional expert failure diagnosis system will be explained with reference to the flowchart shown in FIG.

(1) Step S1 The display device (6) displays an initial failure state selection screen as shown in FIG. The initial failure state selection screen is ``1.Support support, r2.Ready lamp'', r3. CRT no Hyouji Ga Talent” r4. The failure status is roughly categorized and displayed, such as ``NC failure, failure,'' or ``5 degree failure, failure, failure, failure.''

(2) Step S2 The operator selects any item number from 1 to 5 using the input device (1) in accordance with the instruction "Select the fault state" displayed on the initial fault state selection screen. Input the appropriate fault state from the fault states displayed on the initial selection screen.

(3) Step S3 When the item number corresponding to the fault condition is input, the inference engine (3) infers the cause of the fault based on the data stored in the knowledge base (4).

(4) Steps 84 to S5 As a result of the inference, if the inference to the cause of the failure is not reached (step S4), a question regarding the failure condition derived as an intermediate result of the inference is displayed on the failure condition selection screen as shown in Fig. 7. Display (step 35). This failure state selection screen is
1. "Shitoukido Dekirikiki Ugokanai", r 2
, NCREADY ON Dekasousuru”, r 3
It displays questions regarding detailed failure conditions, such as NOREADY ON DEKIKAGAGA HUNTINGSURU. When the operator selects one of the item numbers 1 to 5 using the input device (1) in accordance with the instruction ``Send Tax'' displayed on the failure state selection screen, the inference engine (3) further advances the inference.

As a result of questions regarding detailed failure conditions and answers from the operator being repeated several times, the inference engine (3) obtains a plurality of failure causes and their probabilities as failure diagnosis results.

(5) Steps 86 to S7 The output processing unit (5) creates screen display data for displaying failure causes and their probabilities in text only (Step S6).
, as shown in Figure 8, the cause of failure and its probability are displayed on the display device (
6> (step S7).

The failure causes and their probabilities are displayed using only monochrome characters in descending order of probability, with the item diagnosed as having a high failure probability being the item name, and the inferred failure probability of that item. The failure diagnosis results shown in FIG. 8 indicate that the cause of the failure is a failure in the printed circuit boards MXOI, MXO4, and MXO7, and the probabilities that each of the printed circuit boards MXOL, MXO4, and MX07 are failure are 0.2 g, 0.24 g, and 0.24 g, respectively. It is displayed that it is 0.10.

[Problems to be Solved by the Invention] By the way, as mentioned above, the conventional expert failure diagnosis system only displayed failure causes and their probabilities in text. The problem was that it was difficult to understand.

The present invention has been made to solve the above problems,
It is an object of the present invention to provide an expert failure diagnosis system that displays the probability of a cause of failure displayed as a result of failure diagnosis so that it can be immediately understood.

[Means for Solving the Problems] Therefore, the present invention includes an input means for inputting a failure state, a knowledge base storing data necessary for inferring the cause of the failure, and data and knowledge input by the input means. Based on the data stored in the base, infer the cause of the failure,
An inference engine that outputs the inference results as a cause of failure and a probability of the cause of failure, and a display processing means that corresponds the probability of the cause of failure to the height of the probability and displays the color on the display means. Configure the diagnostic system.

[Operation] In the expert diagnosis system configured as described above, when a fault condition is input from the input means, the inference engine infers the cause of the fault based on the input data and the data stored in the knowledge base. The inference results are output as the cause of failure and the probability of the cause of failure, and the display processing means displays the color on the display means, making the probability of the cause of failure correspond to the height of the probability.

[Example 1] Hereinafter, an example of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a block diagram of an expert failure diagnosis system according to the present invention. In Figure 1, (1) is an input device such as a keyboard through which an operator inputs data such as failure status, (2) is an input processing unit that takes in data input from input device (1), and (3) is an input device. An inference engine (7) infers the cause of failure based on the data taken in by the processing unit (2) and data stored in the knowledge base (4) in advance and outputs the inference result as a diagnosis result. (3) takes in the diagnosis result, determines the display color of the cause of the failure based on the probability of the diagnosis result, and transfers the color to the output processing unit (5) together with the diagnosis result. ) is an output processing unit that generates screen display data for displaying the diagnosis results; (6) is a display device such as a CRT display that displays the cause of failure in different colors according to its probability based on the screen display data; .

Next, the operation of the expert failure diagnosis system according to the present invention will be explained with reference to the flowchart shown in FIG.

(1) Step S1 The display device (6) displays an initial failure state selection screen as shown in FIG. This fault state selection initial screen displays the fault states by roughly classifying them as described above.

(2) Step S2 The operator follows the instructions displayed on the initial fault state selection screen and selects any item number from 1 to 5 using the input device (1) to select the item number displayed on the initial fault state selection screen. Enter the applicable fault condition from the fault conditions.

(3) Step S3 When the item number corresponding to the failure condition is input, the inference engine (3) infers the cause of the failure based on the data stored in the knowledge base (4).

(4) Steps 84 to S5 As a result of the inference, if the inference to the cause of the failure is not reached (step S4), a question regarding the failure condition derived as an intermediate result of the inference is displayed on the failure condition selection screen as shown in Fig. 7. Display (step 85). As described above, this failure state selection screen displays questions regarding detailed failure conditions. When the operator selects any item number from 1 to 5 using the input device (1) according to the instructions displayed on the failure state selection screen, the inference engine (3) further advances the inference.

(5) Steps 86 to S9 The display processing unit (7) determines the color according to the probability of each failure cause.
As shown in FIG. 1, the color to be displayed in the color display area (10) of the display screen is determined (step 96).

This display color is, for example, yellow when the probability of the cause of failure is 0 or more and less than 0.1 (step S7);
When the probability of failure is greater than or equal to 1 and less than 0.2, the color is lit (step S8), and when the probability of the failure cause is greater than or equal to 0.2 and less than 1, the color is colored red (step 89).

(6) Step 910 - Sll The output processing unit (5) creates screen display data for displaying failure causes and their probabilities in different colors (Step 510);
As shown in Figure 3, failure causes and their probabilities are displayed on a display device (6
) (step 811).

The failure diagnosis results shown in FIG. 3 indicate that the cause of the failure is a failure of the printed circuit boards MXOL MXO4 and MXO7, and the probability that each of the printed circuit boards MX[11, MXO4, and MXO7 are failed is 0.28, 0.24, respectively. and 0.10, together with the probability color display corresponding to these probabilities.

In addition, in this embodiment, the screen configuration is such that the color display area for one failure cause obtained as a diagnosis result is a separate area from the failure cause item and probability numerical display item, or the color display area for one failure cause obtained as a diagnosis result is a separate area from the failure cause item and probability numerical display item. Color display may be performed depending on the background color of both or one of them.

Further, in this embodiment, the display color for each probability is determined according to the numerical value of the cause of the failure, but it may be determined according to the order of the magnitude of the probability. For example, the display color of the failure cause with the highest probability of failure cause is red, the display color of the failure cause with the second highest failure cause is lit, the display color of the third highest failure cause is yellow, and the display color of fourth and subsequent failure causes is displayed in green. do.

[Effects of the Invention] As explained above, according to the present invention, the magnitude of the probability of the cause of failure can be intuitively displayed by displaying the failure causes obtained as a result of failure diagnosis in colors according to the height of the probability. As can be seen, this has the effect of providing an expert fault diagnosis system that improves system operability and shortens fault diagnosis time.

[Brief explanation of the drawing]

FIG. 1 is a block diagram of the expert failure diagnosis system according to the present invention, FIG. 2 is a flowchart showing the operation of the expert failure diagnosis system according to the present invention, and FIG. 3 is a diagnosis result display on the display device shown in FIG. 1. An explanatory diagram of the screen, FIG. 4 is a configuration diagram of a conventional expert failure diagnosis system, FIG. 5 is a flowchart showing the operation of the conventional expert failure diagnosis system, and FIG. 6 is an explanatory diagram of the initial failure state selection screen. 8 is an explanatory diagram of a failure state selection screen, and FIG. 8 is an explanatory diagram of a diagnosis result display screen of the display device shown in FIG. 4. In each figure, 1 is an input device, 2 is an input processing unit, 3 is an inference engine, 4 is a knowledge base, 5 is an output processing unit 6 is a display device,
7 is a color display processing section. Note that the same reference numerals in each figure indicate the same or corresponding parts.

Claims (2)

[Claims] (1) An input means for inputting a failure state, a knowledge base storing data necessary for inferring the cause of the failure, and a knowledge base storing data necessary for inferring the cause of the failure, and a method based on the data input by the input means and the data stored in the knowledge base. In an expert failure diagnosis system comprising an inference engine that infers a cause of failure and outputs the inference result as a cause of failure and a probability of the cause of failure, and a display means that displays the diagnosis result, the probability of the cause of failure is calculated. An expert failure diagnosis system characterized by comprising color-coded display processing means for displaying color-coded information on the display means in accordance with the height of the probability. (2) The expert failure diagnosis system according to claim 1, wherein the color-coded display processing means performs color-coded display in accordance with the probability of the cause of the failure.